Analysis of neural networks for edge detection

Autor:	van der Zwaag, B.J., Slump, Cornelis H., Spaanenburg, Lambert
Rok vydání:	2002
Předmět:	Quantitative Biology::Neurons and Cognition Neural Networks EWI-1772 rule extraction Computer Science::Neural and Evolutionary Computation gradient filters IR-43578 Edge detection digital image processing METIS-206911
Zdroj:	13th Annual Workshop on Circuits Systems and Signal Processing (ProRISC), 580-586 STARTPAGE=580;ENDPAGE=586;TITLE=13th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)
Popis:	This paper illustrates a novel method to analyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, the elements of a feedforward-backpropagation neural network, that has been trained to detect edges in images, are described in terms of differential operators of various orders and with various angles of operation.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=narcis______::bef15615d275e2f330dab6af5bae6454 https://research.utwente.nl/en/publications/analysis-of-neural-networks-for-edge-detection(1176b721-0397-4197-8d8d-9a6bd756bd84).html Zobrazit plný text záznamu